The VPERM2F128 is a AVX instruction which permutes between two 256-bit

vectors. It operates on 128-bit elements instead of regular scalar
types. Recognize shuffles that are suitable for VPERM2F128 and teach
the x86 legalizer how to handle them.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@137519 91177308-0d34-0410-b5e6-96231b3b80d8

2 files changed, 25 insertions, 0 deletions

diff --git a/lib/Target/X86/Utils/X86ShuffleDecode.cpp b/lib/Target/X86/Utils/X86ShuffleDecode.cpp
index fe0b3a2..aeb3309 100644
--- a/lib/Target/X86/Utils/X86ShuffleDecode.cpp
+++ b/lib/Target/X86/Utils/X86ShuffleDecode.cpp
@@ -220,4 +220,24 @@ void DecodeVPERMILPDMask(unsigned NumElts, unsigned Imm,
   }
 }
 
+void DecodeVPERM2F128Mask(EVT VT, unsigned Imm,
+                          SmallVectorImpl<unsigned> &ShuffleMask) {
+  unsigned HalfSize = VT.getVectorNumElements()/2;
+  unsigned FstHalfBegin = (Imm & 0x3) * HalfSize;
+  unsigned SndHalfBegin = ((Imm >> 4) & 0x3) * HalfSize;
+
+  for (int i = FstHalfBegin, e = FstHalfBegin+HalfSize; i != e; ++i)
+    ShuffleMask.push_back(i);
+  for (int i = SndHalfBegin, e = SndHalfBegin+HalfSize; i != e; ++i)
+    ShuffleMask.push_back(i);
+}
+
+void DecodeVPERM2F128Mask(unsigned Imm,
+                          SmallVectorImpl<unsigned> &ShuffleMask) {
+  // VPERM2F128 is used by any 256-bit EVT, but X86InstComments only
+  // has information about the instruction and not the types. So for
+  // instruction comments purpose, assume the 256-bit vector is v4i64.
+  return DecodeVPERM2F128Mask(MVT::v4i64, Imm, ShuffleMask);
+}
+
 } // llvm namespace
diff --git a/lib/Target/X86/Utils/X86ShuffleDecode.h b/lib/Target/X86/Utils/X86ShuffleDecode.h
index 1b11c6e..58193e6 100644
--- a/lib/Target/X86/Utils/X86ShuffleDecode.h
+++ b/lib/Target/X86/Utils/X86ShuffleDecode.h
@@ -97,6 +97,11 @@ void DecodeVPERMILPSMask(unsigned NElts, unsigned Imm,
 void DecodeVPERMILPDMask(unsigned NElts, unsigned Imm,
                         SmallVectorImpl<unsigned> &ShuffleMask);
 
+void DecodeVPERM2F128Mask(unsigned Imm,
+                          SmallVectorImpl<unsigned> &ShuffleMask);
+void DecodeVPERM2F128Mask(EVT VT, unsigned Imm,
+                          SmallVectorImpl<unsigned> &ShuffleMask);
+
 } // llvm namespace
 
 #endif